Learning Two-View Stereo Matching

Jianxiong Xiao, Jingni Chen, Dit-Yan Yeung and Long Quan
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong
Computer Vision – ECCV 2008, Lecture Notes in Computer Science, 2008, Volume 5304/2008, 15-27


   title={Learning two-view stereo matching},

   author={Xiao, J. and Chen, J. and Yeung, D.Y. and Quan, L.},

   booktitle={Computer Vision-ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings},







Download Download (PDF)   View View   Source Source   



We propose a graph-based semi-supervised symmetric matching framework that performs dense matching between two uncalibrated wide-baseline images by exploiting the results of sparse matching as labeled data. Our method utilizes multiple sources of information including the underlying manifold structure, matching preference, shapes of the surfaces in the scene, and global epipolar geometric constraints for occlusion handling. It can give inherent sub-pixel accuracy and can be implemented in a parallel fashion on a graphics processing unit (GPU). Since the graphs are directly learned from the input images without relying on extra training data, its performance is very stable and hence the method is applicable under general settings. Our algorithm is robust against outliers in the initial sparse matching due to our consideration of all matching costs simultaneously, and the provision of iterative restarts to reject outliers from the previous estimate. Some challenging experiments have been conducted to evaluate the robustness of our method.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: